© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16527
    Prev
    Next
    INDEX
    Explanations

    shuttle service, shifting, missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    èļ±
    -0.10
    éĿ¢èĨľ
    -0.09
    éļı
    -0.09
    çĴĥ
    -0.09
    ophile
    -0.08
    åī¯éĻ¢éķ¿
    -0.08
    ÑĮ
    -0.08
    塬
    -0.08
    .HTML
    -0.08
    æ´
    -0.08
    POSITIVE LOGITS
    forth
    0.11
    olini
    0.10
     forth
    0.09
    åºĬä¸Ĭ
    0.09
    ously
    0.09
    bred
    0.09
    éĩįä»»
    0.09
    oning
    0.09
    lined
    0.08
    ä¸Ģè¶Ł
    0.08
    Activations Density 0.003%

    No Known Activations